提取聚類信息並合並結果

Question

我試圖在不同數量的集群k的不同矩陣列表上運行聚類算法，並為每次運行提取一些信息。

第一個代碼塊生成不同矩陣的列表

library(tidyverse)
library(cluster)
library(rje)   

dat=mtcars[,1:3]
v_names=names(dat)

combos=rje::powerSet(v_names)

combos=combos[lengths(combos)>1]


df_list=list()

for (i in seq_along(combos)){

  df_list[[i]]=dat[combos[[i]]]
  
  }
gower_ls=lapply(df_list,daisy,metric="gower")

這是我遇到問題的代碼部分

set.seed(4)
model_num <-c(NA)    
sil_width <-c(NA)    
min_sil<-c(NA)    
mincluster<-c(NA)    
k_clusters <-c(NA)    
lowest_sil <-c(NA)    
maxcluster <-c(NA)    
model_vars <- c(NA)

clust_4=lapply(gower_ls,pam,diss=TRUE,k=4)    

for(m in 1:length(clust_4)){
  
  sil_width[m] <-clust_4[[m]][7]$silinfo$avg.width
  
  min_sil[m] <- min(clust_4[[m]][7]$silinfo$clus.avg.widths)
  
  mincluster[m] <-min(clust_4[[m]][6]$clusinfo[,1])
  
  maxcluster[m] <-max(clust_4[[m]][6]$clusinfo[,1])
  
  k_clusters[m]<- nrow(clust_4[[m]][6]$clusinfo)
  
  lowest_sil[m]<-min(clust_4[[m]][7]$silinfo$widths)
  
  model_num[m] <-m
 }    

colresults_4=as.data.frame(cbind( sil_width, min_sil,mincluster,maxcluster,k_clusters,model_num,lowest_sil))

如何將這段代碼轉換為在給定的k范圍內運行？ 我嘗試了嵌套循環，但無法正確編碼。 這是k= 4:6的預期結果，謝謝。

structure(list(sil_width = c(0.766467312788453, 0.543226669407726, 
0.765018469447229, 0.705326458357873, 0.698351173575526, 0.480565022092276, 
0.753366365875066, 0.644345251543097, 0.699437672202048, 0.430310752506775, 
0.678224885117295, 0.576411380463116), min_sil = c(0.539324315243191, 
0.508330909368204, 0.637090842537915, 0.622120627356455, 0.539324315243191, 
0.334047777245833, 0.430814518122641, 0.568591550281139, 0.539324315243191, 
0.295113900268025, 0.430814518122641, 0.19040716086259), mincluster = c(5, 
3, 4, 5, 2, 3, 3, 3, 2, 3, 3, 3), maxcluster = c(14, 12, 11, 
14, 12, 10, 11, 11, 9, 6, 7, 7), k_clusters = c(4, 4, 4, 4, 5, 
5, 5, 5, 6, 6, 6, 6), model_num = c(1, 2, 3, 4, 1, 2, 3, 4, 1, 
2, 3, 4), lowest_sil = c(-0.0726256983240229, 0.0367238314801671, 
0.308069836672298, 0.294247157041013, -0.0726256983240229, -0.122804288130541, 
-0.317748917748917, 0.218164082936686, -0.0726256983240229, -0.224849074123824, 
-0.317748917748917, -0.459909237820881)), row.names = c(NA, -12L
), class = "data.frame")

Answer 1

通過編寫一個函數clus_func來提取集群信息，然后使用purrr包中的cross2和map2 ，我能夠想出一個解決方案：

    library(tidyverse)
    library(cluster)
    library(rje)   
    
    dat=mtcars[,1:3]
    v_names=names(dat)
    
    combos=rje::powerSet(v_names)
    
    combos=combos[lengths(combos)>1]
    
    clus_func=function(x,k){
  
    clust=pam(x,k,diss=TRUE)
    clust_stats=as.data.frame(cbind(
    avg_sil_width=clust$silinfo$avg.width,
    min_clus_width=min(clust$silinfo$clus.avg.widths),
    min_individual_sil=min(clust$silinfo$widths[,3]),
    max_individual_sil=max(clust$silinfo$widths[,3]),
    mincluster= min(clust$clusinfo[,1]),
    maxcluster= max(clust$clusinfo[,1]),
    num_k=max(clust$clustering)  ))       
  
     } 

    
    df_list=list()
    
    for (i in seq_along(combos)){
    
      df_list[[i]]=dat[combos[[i]]]
      
      }
    gower_ls=lapply(df_list,daisy,metric="gower")
        begin_k=4
        end_k=6
        cross_list=cross2(gower_ls,begin_k:end_k)
        
        k=c(NA)
        for(i in 1:length(cross_list)){ k[i]=cross_list[[i]][2]}
        diss=c(NA)
        for(i in 1:length(cross_list)){ diss[i]=cross_list[[i]][1]}
        
        model_stats=map2(diss, k, clus_func)
        model_stats=rbindlist(model_stats)